# coding:utf8
from bs4 import BeautifulSoup
import re
html_doc = """
The Dormouse's storyThe Dormouse's story
Once upon a time there were three little sisters; and their names were
Lacie and
and they lived at the bottom of a well.
...
"""
soup = BeautifulSoup(html_doc,'html.parser',from_encoding='utf-8')
print'获取所有连接'
links = soup.find_all('a')
for link in links:
print link.name,link['href'],link.get_text()
print'获取lacie的连接'
link_node=soup.find('a',href='http://example.com/lacie')
print link_node.name,link_node['href'],link_node.get_text()
print'正则匹配'
link_node=soup.find('a',href=re.compile(r"ill"))
print link_node.name,link_node['href'],link_node.get_text()
print'p段落文字'
p_node=soup.find('a',class_="title")
print p_node.name, p_node.get_text()
会报错 如下
获取所有连接
a http://example.com/elsie Elsie
a http://example.com/lacie Lacie
a http://example.com/tillie Tillie
获取lacie的连接
a http://example.com/lacie Lacie
正则匹配
a http://example.com/tillie Tillie
p段落文字
Traceback (most recent call last):
File "C:\Users\Administrator\workspace\2.7\66\test_bs4.py", line 34, in
print p_node.name, p_node.get_text()
AttributeError: 'NoneType' object has no attribute 'name'